Skip to content
Dashboard

Relace models

Relace is a hosted inference provider for open-weight AI models, delivering cost-efficient access optimized for coding, reasoning, and agentic workloads.
Model
Context
Input
Output
Latency
Throughput
Cache
Search
Capabilities
ZDR
No Training
Regional Inference
Free AI Gateway Credit
Released
1M
$0.03/M
$1/M
3.1 s98 tps
Read$0.01/M
—
+1
09/08/2026
1M
$0.04/M
$0.50/M
1.1 s136 tps
Read$0.03/M
—
+1
08/26/2026
1M
$0.05/M
$12/M
0.5 s99 tps
Read$0.04/M
—
08/18/2026
1M
$0.0046/M
$1.28/M
1.5 s31 tps
Read$0.0046/M
—
+1
07/31/2026
1M
$0.45/M
$13/M
1.1 s123 tps
Read$0.45/M
—
+2
07/16/2026